Privacy-Preserving Policy Synthesis in Markov Decision Processes.
Parham GohariMatthew T. HaleUfuk TopcuPublished in: CoRR (2020)
Keyphrases
- privacy preserving
- markov decision processes
- optimal policy
- policy iteration
- markov decision process
- finite horizon
- average reward
- infinite horizon
- partially observable
- state and action spaces
- action space
- reward function
- average cost
- decision processes
- privacy preserving data mining
- state space
- finite state
- reinforcement learning
- dynamic programming
- total reward
- decision theoretic planning
- markov decision problems
- discounted reward
- policy evaluation
- vertically partitioned data
- transition matrices
- expected reward
- privacy sensitive
- sensitive data
- privacy protection
- stationary policies
- record linkage
- sensitive information
- privacy concerns
- reinforcement learning algorithms
- secure multiparty computation
- privacy preservation
- data privacy
- partially observable markov decision processes
- continuous state spaces
- differential privacy
- long run
- scalar product
- sufficient conditions
- horizontally partitioned data
- stochastic shortest path
- optimal control